|本期目录/Table of Contents|

[1]张 力,邓亚航,饶小李.颜色特征模型在静态车辆检测中的应用[J].武汉工程大学学报,2015,37(01):73-78.[doi:10. 3969/j. issn. 1674-2869. 2015.]
 ,Color feature model in application of static vehicle detection[J].Journal of Wuhan Institute of Technology,2015,37(01):73-78.[doi:10. 3969/j. issn. 1674-2869. 2015.]
点击复制

颜色特征模型在静态车辆检测中的应用(/HTML)
分享到:

《武汉工程大学学报》[ISSN:1674-2869/CN:42-1779/TQ]

卷:
37
期数:
2015年01期
页码:
73-78
栏目:
机电与信息工程
出版日期:
2015-01-31

文章信息/Info

Title:
Color feature model in application of static vehicle detection
文章编号:
1674-2869(2015)01-0073-06
作者:
张 力邓亚航饶小李
昆明理工大学信息工程与自动化学院,云南 昆明 650500
Author(s):
ZHANG LiDENG Ya-hangRAO Xiao-li
Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500,China
关键词:
静态车辆检测颜色特征车辆目标分离
Keywords:
static vehicle detectioncolor featureehicle target separation
分类号:
TN911
DOI:
10. 3969/j. issn. 1674-2869. 2015.
文献标志码:
A
摘要:
为了解决智能交通中的静态车辆检测准确率不高的问题,提出一种基于颜色特征的车辆目标检测方法.该方法首先根据Hough变换分割出路面感兴趣区域,利用颜色特征空间降维建立理想的颜色特征模型;其次,根据贝叶斯分类器进行路面与车辆的像素分类;最后,由最小割/最大流算法进行车辆目标分离.在实景采集交通视频图像后对文中提出方法和现存方法进行了对比评估.基于颜色特征的车辆目标检测方法对于静态车辆目标的检测准确率达到了63.05%,误检率降低至21.27%,漏检率降低至24.01%.与传统方法相比,该方法能更快、更准确地检测到目标.
Abstract:
To improve the low accuracy in static vehicle detection in intelligent transportation, a vehicle targets detection method based on color features was proposed. Firstly, the pavement area of interest was segmented based on Hough transform, and the ideal color feature model was established by using the color feature space dimension reduction. Then, pixels of pavements and vehicles were classfied by Bayesian classifier, and finally the target vehicle was separated by the minimum cut/maximum flow algorithm. We made a comparative assessment of the proposed method with the existed methods after capturing live?蛳action traffic video images. The results show that the detection accuracy is 63.05%, the false rate decreases to 21.27% and the miss rate decreases to 24.01%. Experiments show the proposed method can achieve excellent detection result in static vehicle targets.

参考文献/References:

[1] ZIVKOVIC Z. Improved adaptive Gaussian mixture model for background subtraction[C]//Proceedings of the 17th International Conference on Pattern Recognition, 23-26 August 2004. Piscataway, N.J.:IEEE,2004. 28-31.  [2] TSAI L W,HSIEH J W,FAN K C. Vehicle detection using normalized color and edge map[J]. IEEE Transactions on Image Processing,2007,16(3):850-864.  [3] WANG X Y, ZHANG J L. A traffic incident detection method based on wavelet Mallat algorithm[C]//Proceedings of the 2005 IEEE Mid-Summer Workshop on Soft Computing in Industrial Applications, 28-30 June 2005Piscataway, N.J.:IEEE,2005.166-172.  [4] 樊晓亮, 杨晋吉. 基于帧间差分的背景提取与更新算法[J]. 计算机工程, 2011, 37(22):159-161.   FAN Xiao?鄄liang,YANG Jin?鄄ji. Background extraction and update algorithm based on frame?鄄difference[J]. Computer Engineering,2011,37(22):159-161.(in Chinese)  [5] 杜鉴豪,许力.基于区域光流特征的异常行为检测[J]. 浙江大学学报:工学版, 2011,45(7):1161-1166.  DU Jian-hao,XU Li.Abnormal behavior detection based on regional optical flow[J].Journal of Zhejiang University:Engineering Science, 2011,45(7):1161-1166. (in Chinese)  [6] CHENG S C, YANG C K. A fast and novel technique for color quantization using reduction of color space dimensionality[J]. Pattern Recognition Letters, 2001, 22(8): 845-856.  [7] 赵杰文, 方明, 刘木华,等. 基于Ohta和RGB颜色空间牛胴体背长肌的分割[J]. 江苏大学学报:自然科学版, 2006,27(3):189-192.  ZHAO Jie-wen,FANG Ming,LIU Mu-hua,et al.Segmentation of longissimus dorsi in beef carcass based on Ohta and RGB color systems[J].Journal of Jiangsu University:Natural Science Edition,2006,27(3):189-192. (in Chinese)  [8] 韩萍, 徐建飒. 复杂场景下的极化SAR图像机场跑道检测[J]. 信号处理, 2013(9):1220-1226.  HAN Ping,XU Jian-sa.Runways detection in complex scenes of polarimetric synthetic aperture radar image[J].Journal of Signal Processing,2013(9):1220-1226. (in Chinese)  [9] 孔文杰, 张化祥, 刘丽. 基于图像复杂度和贝叶斯的图像自动标注[J]. 计算机工程与设计, 2014,35(6):2100-2103.  KONG Wen-jie,ZHANG Hua-xiang,LIU Li.Automatic image annotation based on image complexity and Bayesian[J].Computer Engineering and Design,2014,35(6):2100-2103. (in Chinese)  [10] 刘松涛, 殷福亮. 基于图割的图像分割方法及其新进展[J]. 自动化学报, 2012, 38(6): 911-922.  LIU Song-tao,YIN Fu-liang.The basic principle and its new advances of image segmentation methods based on graph cuts[J].Acta Automatica Sinica,2012, 38(6): 911-922. (in Chinese)  [11] 刘杨杨, 谢政, 陈挚. 最大动态流关键弧的改进算法[J]. 计算机应用, 2014,34(4):969-972.  LIU Yang-yang,XIE Zheng,CHEN Zhi.Improved al  gorithm for vital arc of maximum dynamic flow[J].Journal of Computer Applications,2014,34(4):969-972.  (in Chinese)  [12] BOYKOV Y, VEKSLER O, ZABIH R. Fast approximate energy minimization via graph cuts[J]. IEEE Transactions on PMAL Pattern Analysis and Machine Intelligence, 2001,23(11):1222-1239.

相似文献/References:

备注/Memo

备注/Memo:
收稿日期:2014-12-24  基金项目:国家自然科学基金(61063027)  作者简介:张 力(1963-),男,四川成都人,副教授.研究方向:计算机视觉、多媒术技术.
更新日期/Last Update: 2015-03-21